Woody 181f4eca5b feat: Phase 1.3 query pipeline with decomposition, relevance filter, and response ... - Add QueryDecomposer: extracts keywords from question via LLM JSON response - Add RelevanceFilter: batch scores chunks 0-10, filters by threshold - Add POST /api/v1/query endpoint with full 3-step pipeline: 1. QueryDecomposer.decompose() → keywords 2. RAGService.retrieve() → chunks from ChromaDB 3. RelevanceFilter.filter() → score and filter chunks 4. RAGService.generate_response() → bullet-point answer - Fix SourceMetadata.upload_date type from datetime to str for flexibility - Test-first: 13 new tests pass (5 decomposer, 5 relevance filter, 3 query endpoint) - All Phase 1 tests: 41 passed, 2 skipped		2026-04-22 17:19:21 +08:00
..
app	feat: Phase 1.3 query pipeline with decomposition, relevance filter, and response	2026-04-22 17:19:21 +08:00
uploads	chore: add .gitignore with Python, Node, env, and ChromaDB exclusions	2026-04-22 15:57:04 +08:00
.env.example	feat: Phase 1.1 project setup with config, database, and models	2026-04-22 16:13:52 +08:00
pytest.ini	feat: Phase 1.2 ingestion pipeline with chunking and metadata	2026-04-22 16:49:52 +08:00
requirements.txt	feat: Phase 1.1 project setup with config, database, and models	2026-04-22 16:13:52 +08:00